BibTeX: David Kotz papers for project 'armada'.
For more information, visit this web page:
https://www.cs.dartmouth.edu/~kotz/research/project/armada/index.html

@TechReport{kotz:app-pario,
  author =        {David Kotz},
  title =         {{Applications of Parallel I/O}},
  institution =   {Dartmouth Computer Science},
  year =          1996,
  month =         {October},
  number =        {PCS-TR96-297},
  copyright =     {David Kotz},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/kotz-app-pario/index.html},
  note =          {Release 1},
  abstract =      {Scientific applications are increasingly being implemented on massively parallel supercomputers. Many of these applications have intense I/O demands, as well as massive computational requirements. This paper is essentially an annotated bibliography of papers and other sources of information about scientific applications using parallel I/O. It will be updated periodically.},
}

@TechReport{oldfield:app-pario,
  author =        {Ron Oldfield and David Kotz},
  title =         {{Applications of Parallel I/O}},
  institution =   {Dartmouth Computer Science},
  year =          1998,
  month =         {August},
  number =        {PCS-TR98-337},
  copyright =     {the authors},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-app-pario/index.html},
  note =          {Supplement to PCS-TR96-297},
  abstract =      {Scientific applications are increasingly being implemented on massively parallel supercomputers. Many of these applications have intense I/O demands, as well as massive computational requirements. This paper is essentially an annotated bibliography of papers and other sources of information about scientific applications using parallel I/O. It will be updated periodically.},
}

@InProceedings{oldfield:armada,
  author =        {Ron Oldfield and David Kotz},
  title =         {{Armada: A parallel file system for computational grids}},
  booktitle =     {{Proceedings of the IEEE/ACM International Symposium on Cluster Computing and the Grid (ccGrid)}},
  year =          2001,
  month =         {May},
  pages =         {194--201},
  publisher =     {IEEE},
  copyright =     {IEEE},
  address =       {Brisbane, Australia},
  DOI =           {10.1109/CCGRID.2001.923193},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-armada/index.html},
  abstract =      {High-performance distributed computing appears to be shifting away from tightly-connected supercomputers to computational grids composed of heterogeneous systems of networks, computers, storage devices, and various other devices that collectively act as a single geographically distributed virtual computer. One of the great challenges for this environment is providing efficient parallel data access to remote distributed datasets. In this paper, we discuss some of the issues associated with parallel I/O and computatational grids and describe the design of a flexible parallel file system that allows the application to control the behavior and functionality of virtually all aspects of the file system.},
}

@InCollection{oldfield:bapp-pario,
  author =        {Ron Oldfield and David Kotz},
  title =         {{Scientific Applications using Parallel I/O}},
  booktitle =     {{High Performance Mass Storage and Parallel I/O: Technologies and Applications}},
  editor =        {Hai Jin and Toni Cortes and Rajkumar Buyya},
  year =          2001,
  month =         {September},
  chapter =       45,
  pages =         {655--666},
  publisher =     {Wiley-IEEE Press},
  copyright =     {Wiley-IEEE Press},
  ISBN13 =        {978-0-471-20809-9},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-bapp-pario/index.html},
  abstract =      {Scientific applications are increasingly being implemented on massively parallel supercomputers. Many of these applications have intense I/O demands, as well as massive computational requirements. This paper is essentially an annotated bibliography of papers and other sources of information about scientific applications using parallel I/O.},
}

@TechReport{oldfield:emulab-tr,
  author =        {Ron Oldfield and David Kotz},
  title =         {{Using the Emulab network testbed to evaluate the Armada I/O framework for computational grids}},
  institution =   {Dartmouth Computer Science},
  year =          2002,
  month =         {September},
  number =        {TR2002-433},
  copyright =     {the authors},
  address =       {Hanover, NH},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-emulab-tr/index.html},
  abstract =      {This short report describes our experiences using the Emulab network testbed at the University of Utah to test performance of the Armada framework for parallel I/O on computational grids.},
}

@Article{oldfield:framework,
  author =        {Ron Oldfield and David Kotz},
  title =         {{Armada: a parallel I/O framework for computational grids}},
  journal =       {Future Generation Computing Systems (FGCS)},
  year =          2002,
  month =         {March},
  volume =        18,
  number =        4,
  pages =         {501--523},
  publisher =     {Elsevier Science Press},
  copyright =     {Elsevier Science},
  DOI =           {10.1016/S0167-739X(01)00076-0},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-framework/index.html},
  abstract =      {High-performance computing increasingly occurs on ``computational grids'' composed of heterogeneous and geographically distributed systems of computers, networks, and storage devices that collectively act as a single ``virtual'' computer. One of the great challenges for this environment is to provide efficient access to data that is distributed across remote data servers in a grid. In this paper, we describe our solution, a framework we call Armada. Armada allows applications to flexibly compose modules to access their data, and to place those modules at appropriate hosts within the grid to reduce network traffic.},
}

@Article{oldfield:restruct,
  author =        {Ron Oldfield and David Kotz},
  title =         {{Improving data access for computational grid applications}},
  journal =       {Cluster Computing},
  year =          2006,
  month =         {January},
  volume =        9,
  number =        1,
  pages =         {79--99},
  publisher =     {Springer},
  copyright =     {Springer},
  DOI =           {10.1007/s10586-006-4899-7},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-restruct/index.html},
  abstract =      {High-performance computing increasingly occurs on ``computational grids'' composed of heterogeneous and geographically distributed systems of computers, networks, and storage devices that collectively act as a single ``virtual'' computer. A key challenge in this environment is to provide efficient access to data distributed across remote data servers. Our parallel I/O framework, called Armada, allows application and data-set providers to flexibly compose graphs of processing modules that describe the distribution, application interfaces, and processing required of the dataset before computation. Although the framework provides a simple programming model for the application programmer and the data-set provider, the resulting graph may contain bottlenecks that prevent efficient data access. In this paper, we present an algorithm used to restructure Armada graphs that distributes computation and data flow to improve performance in the context of a wide-area computational grid.},
}

@PhdThesis{oldfield:thesis,
  author =        {Ron Oldfield},
  title =         {{Efficient I/O for Computational Grid Applications}},
  school =        {Dartmouth Computer Science},
  year =          2003,
  month =         {May},
  copyright =     {Ron Oldfield},
  address =       {Hanover, NH},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-thesis/index.html},
  note =          {Available as Dartmouth Computer Science Technical Report TR2003-459},
  abstract =      {High-performance computing increasingly occurs on ``computational grids'' composed of heterogeneous and geographically distributed systems of computers, networks, and storage devices that collectively act as a single ``virtual'' computer. A key challenge in this environment is to provide efficient access to data distributed across remote data servers. This dissertation explores some of the issues associated with I/O for wide-area distributed computing and describes an I/O system, called Armada, with the following features: a framework to allow application and dataset providers to flexibly compose graphs of processing modules that describe the distribution, application interfaces, and processing required of the dataset before or after computation; an algorithm to restructure application graphs to increase parallelism and to improve network performance in a wide-area network; and a hierarchical graph-partitioning scheme that deploys components of the application graph in a way that is both beneficial to the application and sensitive to the administrative policies of the different administrative domains. Experiments show that applications using Armada perform well in both low- and high-bandwidth environments, and that our approach does an exceptional job of hiding the network latency inherent in grid computing.},
}

@InProceedings{oldfield:wip,
  author =        {Ron Oldfield and David Kotz},
  title =         {{The Armada framework for parallel I/O on computational grids}},
  booktitle =     {{Proceedings of the USENIX Conference on File and Storage Technologies (FAST)}},
  year =          2002,
  month =         {January},
  publisher =     {USENIX Association},
  copyright =     {the authors},
  location =      {Monterrey, CA},
  URL =           {https://www.cs.dartmouth.edu/~kotz/research/oldfield-wip/index.html},
  note =          {Work-in-progress report},
}